dupe-hunter 0.1.0__tar.gz

dupe_hunter-0.1.0/PKG-INFO

@@ -0,0 +1,62 @@
+Metadata-Version: 2.4
+Name: dupe-hunter
+Version: 0.1.0
+Summary: Find and remove duplicate files quickly
+Author-email: lalalaleishaaa <your-email@example.com>
+License: MIT
+Project-URL: Homepage, https://github.com/lalalaleishaaa/dupe-hunter
+Project-URL: Bug Tracker, https://github.com/lalalaleishaaa/dupe-hunter/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Description-Content-Type: text/markdown
+Requires-Dist: typer>=0.9.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: click>=8.0.0
+
+\# 🔍 Dupe Hunter
+
+
+
+\*\*Find and delete duplicate files in seconds!\*\* 
+
+
+
+\##  Real Results
+
+
+
+I ran this on my own computer and:
+
+\-  Found \*\*16,541 duplicate files\*\*
+
+\-  Saved \*\*3.1 GB\*\* of disk space
+
+\-  Scanned \*\*50,000+ files\*\* in minutes
+
+
+
+\##  Features
+
+
+
+\- \*\*Blazing fast\*\* - Groups by file size first
+
+\- \*\*Progress bars\*\* - See what's happening
+
+\- \*\*Beautiful output\*\* - Color-coded tables
+
+\- \*\*Space calculator\*\* - Shows how much you'll save
+
+\- \*\*Safe delete\*\* - Keeps first file, deletes rest
+
+
+
+\##  Installation
+
+
+
+```bash
+
+pip install dupe-hunter
+

dupe_hunter-0.1.0/README.md

@@ -0,0 +1,46 @@
+\# 🔍 Dupe Hunter
+
+
+
+\*\*Find and delete duplicate files in seconds!\*\* 
+
+
+
+\##  Real Results
+
+
+
+I ran this on my own computer and:
+
+\-  Found \*\*16,541 duplicate files\*\*
+
+\-  Saved \*\*3.1 GB\*\* of disk space
+
+\-  Scanned \*\*50,000+ files\*\* in minutes
+
+
+
+\##  Features
+
+
+
+\- \*\*Blazing fast\*\* - Groups by file size first
+
+\- \*\*Progress bars\*\* - See what's happening
+
+\- \*\*Beautiful output\*\* - Color-coded tables
+
+\- \*\*Space calculator\*\* - Shows how much you'll save
+
+\- \*\*Safe delete\*\* - Keeps first file, deletes rest
+
+
+
+\##  Installation
+
+
+
+```bash
+
+pip install dupe-hunter
+

dupe_hunter-0.1.0/pyproject.toml

@@ -0,0 +1,30 @@
+[build-system]
+requires = ["setuptools>=61.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "dupe-hunter"
+version = "0.1.0"
+description = "Find and remove duplicate files quickly"
+readme = "README.md"
+authors = [
+    {name = "lalalaleishaaa", email = "your-email@example.com"}
+]
+license = {text = "MIT"}
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: MIT License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "typer>=0.9.0",
+    "rich>=13.0.0",
+    "click>=8.0.0"
+]
+
+[project.urls]
+Homepage = "https://github.com/lalalaleishaaa/dupe-hunter"
+"Bug Tracker" = "https://github.com/lalalaleishaaa/dupe-hunter/issues"
+
+[project.scripts]
+dupe-hunter = "src.dupe_hunter:app"

dupe_hunter-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

dupe_hunter-0.1.0/setup.py

@@ -0,0 +1,3 @@
+from setuptools import setup
+
+setup()

dupe_hunter-0.1.0/src/__init__.py

@@ -0,0 +1 @@
+# This makes 'src' a proper Python package

dupe_hunter-0.1.0/src/dupe_hunter.egg-info/PKG-INFO

@@ -0,0 +1,62 @@
+Metadata-Version: 2.4
+Name: dupe-hunter
+Version: 0.1.0
+Summary: Find and remove duplicate files quickly
+Author-email: lalalaleishaaa <your-email@example.com>
+License: MIT
+Project-URL: Homepage, https://github.com/lalalaleishaaa/dupe-hunter
+Project-URL: Bug Tracker, https://github.com/lalalaleishaaa/dupe-hunter/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Description-Content-Type: text/markdown
+Requires-Dist: typer>=0.9.0
+Requires-Dist: rich>=13.0.0
+Requires-Dist: click>=8.0.0
+
+\# 🔍 Dupe Hunter
+
+
+
+\*\*Find and delete duplicate files in seconds!\*\* 
+
+
+
+\##  Real Results
+
+
+
+I ran this on my own computer and:
+
+\-  Found \*\*16,541 duplicate files\*\*
+
+\-  Saved \*\*3.1 GB\*\* of disk space
+
+\-  Scanned \*\*50,000+ files\*\* in minutes
+
+
+
+\##  Features
+
+
+
+\- \*\*Blazing fast\*\* - Groups by file size first
+
+\- \*\*Progress bars\*\* - See what's happening
+
+\- \*\*Beautiful output\*\* - Color-coded tables
+
+\- \*\*Space calculator\*\* - Shows how much you'll save
+
+\- \*\*Safe delete\*\* - Keeps first file, deletes rest
+
+
+
+\##  Installation
+
+
+
+```bash
+
+pip install dupe-hunter
+

dupe_hunter-0.1.0/src/dupe_hunter.egg-info/SOURCES.txt

@@ -0,0 +1,11 @@
+README.md
+pyproject.toml
+setup.py
+src/__init__.py
+src/dupe_hunter.py
+src/dupe_hunter.egg-info/PKG-INFO
+src/dupe_hunter.egg-info/SOURCES.txt
+src/dupe_hunter.egg-info/dependency_links.txt
+src/dupe_hunter.egg-info/entry_points.txt
+src/dupe_hunter.egg-info/requires.txt
+src/dupe_hunter.egg-info/top_level.txt

dupe_hunter-0.1.0/src/dupe_hunter.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

dupe_hunter-0.1.0/src/dupe_hunter.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+dupe-hunter = src.dupe_hunter:app

dupe_hunter-0.1.0/src/dupe_hunter.egg-info/requires.txt

@@ -0,0 +1,3 @@
+typer>=0.9.0
+rich>=13.0.0
+click>=8.0.0

dupe_hunter-0.1.0/src/dupe_hunter.egg-info/top_level.txt

@@ -0,0 +1,2 @@
+__init__
+dupe_hunter

dupe_hunter-0.1.0/src/dupe_hunter.py

@@ -0,0 +1,168 @@
+import typer
+from pathlib import Path
+import hashlib
+from rich.progress import track
+from rich.console import Console
+from rich.table import Table
+from collections import defaultdict
+
+# Fix for when running as installed package
+import sys
+sys.path.insert(0, str(Path(__file__).parent.parent))
+
+app = typer.Typer()
+console = Console()
+
+def get_file_hash(filepath: Path):
+    hasher = hashlib.md5()
+    try:
+        with open(filepath, 'rb') as f:
+            for chunk in iter(lambda: f.read(8192), b''):
+                hasher.update(chunk)
+        return hasher.hexdigest()
+    except (PermissionError, OSError):
+        return None
+
+@app.command()
+def scan(
+    folder: str = typer.Argument(".", help="Folder to scan for duplicates"),
+    delete: bool = typer.Option(False, "--delete", help="Delete duplicate files (keeps the first one)")
+):
+    """Find duplicate files in a folder."""
+    console.print(f"[bold blue]📂 Scanning:[/bold blue] {folder}")
+    
+    folder_path = Path(folder)
+    if not folder_path.exists():
+        console.print(f"[red]❌ Error:[/red] Folder '{folder}' doesn't exist!")
+        return
+    
+    all_files = [f for f in folder_path.rglob("*") if f.is_file()]
+    
+    if not all_files:
+        console.print("[yellow]⚠️  No files found![/yellow]")
+        return
+    
+    console.print(f"Found [green]{len(all_files)}[/green] files")
+    
+    size_groups = defaultdict(list)
+    for file in track(all_files, description="Grouping by size..."):
+        size_groups[file.stat().st_size].append(file)
+    
+    potential_dupes = {
+        size: files 
+        for size, files in size_groups.items() 
+        if len(files) > 1
+    }
+    
+    if not potential_dupes:
+        console.print("[green]✅ No duplicates found![/green]")
+        return
+    
+    console.print(f"Found [yellow]{len(potential_dupes)}[/yellow] size groups")
+    
+    duplicates = defaultdict(list)
+    for size, files in track(potential_dupes.items(), description="Hashing..."):
+        hash_groups = defaultdict(list)
+        for file in files:
+            file_hash = get_file_hash(file)
+            if file_hash:
+                hash_groups[file_hash].append(file)
+        
+        for file_hash, dup_files in hash_groups.items():
+            if len(dup_files) > 1:
+                duplicates[file_hash] = dup_files
+    
+    if not duplicates:
+        console.print("[green]✅ No exact duplicates found![/green]")
+        return
+    
+    total_dupes = sum(len(files) for files in duplicates.values())
+    console.print(f"\n[bold red]🔍 Found {total_dupes} duplicates in {len(duplicates)} groups:\n")
+    
+    for file_hash, files in duplicates.items():
+        table = Table(title=f"Hash: {file_hash[:8]}...")
+        table.add_column("File", style="cyan")
+        table.add_column("Size", style="green")
+        
+        for f in files:
+            size_kb = f.stat().st_size / 1024
+            if size_kb > 1024:
+                size_mb = size_kb / 1024
+                table.add_row(str(f), f"{size_mb:.2f} MB")
+            else:
+                table.add_row(str(f), f"{size_kb:.2f} KB")
+        
+        console.print(table)
+        console.print("─" * 50)
+    
+    # ==============================================
+    # NEW: Calculate and display space savings
+    # ==============================================
+    
+    # Calculate total space wasted
+    total_size = 0
+    total_savings = 0
+    
+    for file_hash, files in duplicates.items():
+        # Size of all duplicate files in this group
+        group_size = sum(f.stat().st_size for f in files)
+        total_size += group_size
+        
+        # Keep one copy, delete the rest
+        # So savings = group_size - size_of_one_file
+        group_savings = group_size - files[0].stat().st_size
+        total_savings += group_savings
+    
+    # Display the savings
+    if total_savings > 0:
+        console.print("")
+        if total_savings > 1024 * 1024:  # More than 1 MB
+            console.print(f"[bold yellow]💾 Potential space saved: {total_savings / (1024 * 1024):.2f} MB[/bold yellow]")
+        elif total_savings > 1024:  # More than 1 KB
+            console.print(f"[bold yellow]💾 Potential space saved: {total_savings / 1024:.2f} KB[/bold yellow]")
+        else:
+            console.print(f"[bold yellow]💾 Potential space saved: {total_savings} bytes[/bold yellow]")
+        
+        console.print(f"[bold cyan]📊 SUMMARY[/bold cyan]")
+        console.print(f"   Total duplicate groups: [yellow]{len(duplicates)}[/yellow]")
+        console.print(f"   Total duplicate files: [yellow]{total_dupes}[/yellow]")
+        
+        if total_savings > 1024 * 1024:
+            console.print(f"   Total space wasted: [yellow]{total_savings / (1024 * 1024):.2f} MB[/yellow]")
+        elif total_savings > 1024:
+            console.print(f"   Total space wasted: [yellow]{total_savings / 1024:.2f} KB[/yellow]")
+        else:
+            console.print(f"   Total space wasted: [yellow]{total_savings} bytes[/yellow]")
+    
+    # ==============================================
+    # END OF NEW CODE
+    # ==============================================
+    
+    # If delete flag is used, remove duplicates
+    if delete:
+        console.print("\n[bold yellow]⚠️  DELETE MODE ACTIVATED[/bold yellow]")
+        console.print("[yellow]Keeping the first file in each group, deleting the rest...[/yellow]")
+        
+        deleted_count = 0
+        for file_hash, files in duplicates.items():
+            # Keep first file, delete the rest
+            for file in files[1:]:
+                try:
+                    file.unlink()
+                    console.print(f"[red]🗑️  Deleted:[/red] {file}")
+                    deleted_count += 1
+                except Exception as e:
+                    console.print(f"[red]❌ Error:[/red] {e}")
+        
+        if deleted_count > 0:
+            console.print(f"\n[bold green]✅ Deleted {deleted_count} duplicate files![/bold green]")
+            console.print(f"[bold green]💾 Saved {total_savings / (1024 * 1024):.2f} MB of space![/bold green]")
+        else:
+            console.print("\n[yellow]No files were deleted.[/yellow]")
+
+@app.command()
+def hello(name: str = "World"):
+    console.print(f"[bold green]Hello {name}! 🚀[/bold green]")
+
+if __name__ == "__main__":
+    app()